效率 on ZRJ | 学习笔记

Javascript 执行一次 MD5 或 SHA1 需要多久

Wed, 03 Apr 2013 15:16:44 +0800

首先是 Javascript 算 MD5 的问题，看到这里，http://pajhome.org.uk/crypt/md5/，于是就是加一个时间打点，然后跑了

<script>

/*
 * A JavaScript implementation of the RSA Data Security, Inc. MD5 Message
 * Digest Algorithm, as defined in RFC 1321.
 * Version 2.2 Copyright (C) Paul Johnston 1999 - 2009
 * Other contributors: Greg Holt, Andrew Kepert, Ydnar, Lostinet
 * Distributed under the BSD License
 * See http://pajhome.org.uk/crypt/md5 for more info.
 */

/*
 * Configurable variables. You may need to tweak these to be compatible with
 * the server-side, but the defaults work in most cases.
 */
var hexcase = 0;   /* hex output format. 0 - lowercase; 1 - uppercase        */
var b64pad  = "";  /* base-64 pad character. "=" for strict RFC compliance   */

/*
 * These are the functions you'll usually want to call
 * They take string arguments and return either hex or base-64 encoded strings
 */
function hex_md5(s)    { return rstr2hex(rstr_md5(str2rstr_utf8(s))); }
function b64_md5(s)    { return rstr2b64(rstr_md5(str2rstr_utf8(s))); }
function any_md5(s, e) { return rstr2any(rstr_md5(str2rstr_utf8(s)), e); }
function hex_hmac_md5(k, d)
  { return rstr2hex(rstr_hmac_md5(str2rstr_utf8(k), str2rstr_utf8(d))); }
function b64_hmac_md5(k, d)
  { return rstr2b64(rstr_hmac_md5(str2rstr_utf8(k), str2rstr_utf8(d))); }
function any_hmac_md5(k, d, e)
  { return rstr2any(rstr_hmac_md5(str2rstr_utf8(k), str2rstr_utf8(d)), e); }

/*
 * Perform a simple self-test to see if the VM is working
 */
function md5_vm_test()
{
  return hex_md5("abc").toLowerCase() == "900150983cd24fb0d6963f7d28e17f72";
}

/*
 * Calculate the MD5 of a raw string
 */
function rstr_md5(s)
{
  return binl2rstr(binl_md5(rstr2binl(s), s.length * 8));
}

/*
 * Calculate the HMAC-MD5, of a key and some data (raw strings)
 */
function rstr_hmac_md5(key, data)
{
  var bkey = rstr2binl(key);
  if(bkey.length > 16) bkey = binl_md5(bkey, key.length * 8);

  var ipad = Array(16), opad = Array(16);
  for(var i = 0; i < 16; i++)
  {
    ipad[i] = bkey[i] ^ 0x36363636;
    opad[i] = bkey[i] ^ 0x5C5C5C5C;
  }

  var hash = binl_md5(ipad.concat(rstr2binl(data)), 512 + data.length * 8);
  return binl2rstr(binl_md5(opad.concat(hash), 512 + 128));
}

/*
 * Convert a raw string to a hex string
 */
function rstr2hex(input)
{
  try { hexcase } catch(e) { hexcase=0; }
  var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
  var output = "";
  var x;
  for(var i = 0; i < input.length; i++)
  {
    x = input.charCodeAt(i);
    output += hex_tab.charAt((x >>> 4) & 0x0F)
           +  hex_tab.charAt( x        & 0x0F);
  }
  return output;
}

/*
 * Convert a raw string to a base-64 string
 */
function rstr2b64(input)
{
  try { b64pad } catch(e) { b64pad=''; }
  var tab = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
  var output = "";
  var len = input.length;
  for(var i = 0; i < len; i += 3)
  {
    var triplet = (input.charCodeAt(i) << 16)
                | (i + 1 < len ? input.charCodeAt(i+1) << 8 : 0)
                | (i + 2 < len ? input.charCodeAt(i+2)      : 0);
    for(var j = 0; j < 4; j++)
    {
      if(i * 8 + j * 6 > input.length * 8) output += b64pad;
      else output += tab.charAt((triplet >>> 6*(3-j)) & 0x3F);
    }
  }
  return output;
}

/*
 * Convert a raw string to an arbitrary string encoding
 */
function rstr2any(input, encoding)
{
  var divisor = encoding.length;
  var i, j, q, x, quotient;

  /* Convert to an array of 16-bit big-endian values, forming the dividend */
  var dividend = Array(Math.ceil(input.length / 2));
  for(i = 0; i < dividend.length; i++)
  {
    dividend[i] = (input.charCodeAt(i * 2) << 8) | input.charCodeAt(i * 2 + 1);
  }

  /*
   * Repeatedly perform a long division. The binary array forms the dividend,
   * the length of the encoding is the divisor. Once computed, the quotient
   * forms the dividend for the next step. All remainders are stored for later
   * use.
   */
  var full_length = Math.ceil(input.length * 8 /
                                    (Math.log(encoding.length) / Math.log(2)));
  var remainders = Array(full_length);
  for(j = 0; j < full_length; j++)
  {
    quotient = Array();
    x = 0;
    for(i = 0; i < dividend.length; i++)
    {
      x = (x << 16) + dividend[i];
      q = Math.floor(x / divisor);
      x -= q * divisor;
      if(quotient.length > 0 || q > 0)
        quotient[quotient.length] = q;
    }
    remainders[j] = x;
    dividend = quotient;
  }

  /* Convert the remainders to the output string */
  var output = "";
  for(i = remainders.length - 1; i >= 0; i--)
    output += encoding.charAt(remainders[i]);

  return output;
}

/*
 * Encode a string as utf-8.
 * For efficiency, this assumes the input is valid utf-16.
 */
function str2rstr_utf8(input)
{
  var output = "";
  var i = -1;
  var x, y;

  while(++i < input.length)
  {
    /* Decode utf-16 surrogate pairs */
    x = input.charCodeAt(i);
    y = i + 1 < input.length ? input.charCodeAt(i + 1) : 0;
    if(0xD800 <= x && x <= 0xDBFF && 0xDC00 <= y && y <= 0xDFFF)
    {
      x = 0x10000 + ((x & 0x03FF) << 10) + (y & 0x03FF);
      i++;
    }

    /* Encode output as utf-8 */
    if(x <= 0x7F)
      output += String.fromCharCode(x);
    else if(x <= 0x7FF)
      output += String.fromCharCode(0xC0 | ((x >>> 6 ) & 0x1F),
                                    0x80 | ( x         & 0x3F));
    else if(x <= 0xFFFF)
      output += String.fromCharCode(0xE0 | ((x >>> 12) & 0x0F),
                                    0x80 | ((x >>> 6 ) & 0x3F),
                                    0x80 | ( x         & 0x3F));
    else if(x <= 0x1FFFFF)
      output += String.fromCharCode(0xF0 | ((x >>> 18) & 0x07),
                                    0x80 | ((x >>> 12) & 0x3F),
                                    0x80 | ((x >>> 6 ) & 0x3F),
                                    0x80 | ( x         & 0x3F));
  }
  return output;
}

/*
 * Encode a string as utf-16
 */
function str2rstr_utf16le(input)
{
  var output = "";
  for(var i = 0; i < input.length; i++)
    output += String.fromCharCode( input.charCodeAt(i)        & 0xFF,
                                  (input.charCodeAt(i) >>> 8) & 0xFF);
  return output;
}

function str2rstr_utf16be(input)
{
  var output = "";
  for(var i = 0; i < input.length; i++)
    output += String.fromCharCode((input.charCodeAt(i) >>> 8) & 0xFF,
                                   input.charCodeAt(i)        & 0xFF);
  return output;
}

/*
 * Convert a raw string to an array of little-endian words
 * Characters >255 have their high-byte silently ignored.
 */
function rstr2binl(input)
{
  var output = Array(input.length >> 2);
  for(var i = 0; i < output.length; i++)
    output[i] = 0;
  for(var i = 0; i < input.length * 8; i += 8)
    output[i>>5] |= (input.charCodeAt(i / 8) & 0xFF) << (i%32);
  return output;
}

/*
 * Convert an array of little-endian words to a string
 */
function binl2rstr(input)
{
  var output = "";
  for(var i = 0; i < input.length * 32; i += 8)
    output += String.fromCharCode((input[i>>5] >>> (i % 32)) & 0xFF);
  return output;
}

/*
 * Calculate the MD5 of an array of little-endian words, and a bit length.
 */
function binl_md5(x, len)
{
  /* append padding */
  x[len >> 5] |= 0x80 << ((len) % 32);
  x[(((len + 64) >>> 9) << 4) + 14] = len;

  var a =  1732584193;
  var b = -271733879;
  var c = -1732584194;
  var d =  271733878;

  for(var i = 0; i < x.length; i += 16)
  {
    var olda = a;
    var oldb = b;
    var oldc = c;
    var oldd = d;

    a = md5_ff(a, b, c, d, x[i+ 0], 7 , -680876936);
    d = md5_ff(d, a, b, c, x[i+ 1], 12, -389564586);
    c = md5_ff(c, d, a, b, x[i+ 2], 17,  606105819);
    b = md5_ff(b, c, d, a, x[i+ 3], 22, -1044525330);
    a = md5_ff(a, b, c, d, x[i+ 4], 7 , -176418897);
    d = md5_ff(d, a, b, c, x[i+ 5], 12,  1200080426);
    c = md5_ff(c, d, a, b, x[i+ 6], 17, -1473231341);
    b = md5_ff(b, c, d, a, x[i+ 7], 22, -45705983);
    a = md5_ff(a, b, c, d, x[i+ 8], 7 ,  1770035416);
    d = md5_ff(d, a, b, c, x[i+ 9], 12, -1958414417);
    c = md5_ff(c, d, a, b, x[i+10], 17, -42063);
    b = md5_ff(b, c, d, a, x[i+11], 22, -1990404162);
    a = md5_ff(a, b, c, d, x[i+12], 7 ,  1804603682);
    d = md5_ff(d, a, b, c, x[i+13], 12, -40341101);
    c = md5_ff(c, d, a, b, x[i+14], 17, -1502002290);
    b = md5_ff(b, c, d, a, x[i+15], 22,  1236535329);

    a = md5_gg(a, b, c, d, x[i+ 1], 5 , -165796510);
    d = md5_gg(d, a, b, c, x[i+ 6], 9 , -1069501632);
    c = md5_gg(c, d, a, b, x[i+11], 14,  643717713);
    b = md5_gg(b, c, d, a, x[i+ 0], 20, -373897302);
    a = md5_gg(a, b, c, d, x[i+ 5], 5 , -701558691);
    d = md5_gg(d, a, b, c, x[i+10], 9 ,  38016083);
    c = md5_gg(c, d, a, b, x[i+15], 14, -660478335);
    b = md5_gg(b, c, d, a, x[i+ 4], 20, -405537848);
    a = md5_gg(a, b, c, d, x[i+ 9], 5 ,  568446438);
    d = md5_gg(d, a, b, c, x[i+14], 9 , -1019803690);
    c = md5_gg(c, d, a, b, x[i+ 3], 14, -187363961);
    b = md5_gg(b, c, d, a, x[i+ 8], 20,  1163531501);
    a = md5_gg(a, b, c, d, x[i+13], 5 , -1444681467);
    d = md5_gg(d, a, b, c, x[i+ 2], 9 , -51403784);
    c = md5_gg(c, d, a, b, x[i+ 7], 14,  1735328473);
    b = md5_gg(b, c, d, a, x[i+12], 20, -1926607734);

    a = md5_hh(a, b, c, d, x[i+ 5], 4 , -378558);
    d = md5_hh(d, a, b, c, x[i+ 8], 11, -2022574463);
    c = md5_hh(c, d, a, b, x[i+11], 16,  1839030562);
    b = md5_hh(b, c, d, a, x[i+14], 23, -35309556);
    a = md5_hh(a, b, c, d, x[i+ 1], 4 , -1530992060);
    d = md5_hh(d, a, b, c, x[i+ 4], 11,  1272893353);
    c = md5_hh(c, d, a, b, x[i+ 7], 16, -155497632);
    b = md5_hh(b, c, d, a, x[i+10], 23, -1094730640);
    a = md5_hh(a, b, c, d, x[i+13], 4 ,  681279174);
    d = md5_hh(d, a, b, c, x[i+ 0], 11, -358537222);
    c = md5_hh(c, d, a, b, x[i+ 3], 16, -722521979);
    b = md5_hh(b, c, d, a, x[i+ 6], 23,  76029189);
    a = md5_hh(a, b, c, d, x[i+ 9], 4 , -640364487);
    d = md5_hh(d, a, b, c, x[i+12], 11, -421815835);
    c = md5_hh(c, d, a, b, x[i+15], 16,  530742520);
    b = md5_hh(b, c, d, a, x[i+ 2], 23, -995338651);

    a = md5_ii(a, b, c, d, x[i+ 0], 6 , -198630844);
    d = md5_ii(d, a, b, c, x[i+ 7], 10,  1126891415);
    c = md5_ii(c, d, a, b, x[i+14], 15, -1416354905);
    b = md5_ii(b, c, d, a, x[i+ 5], 21, -57434055);
    a = md5_ii(a, b, c, d, x[i+12], 6 ,  1700485571);
    d = md5_ii(d, a, b, c, x[i+ 3], 10, -1894986606);
    c = md5_ii(c, d, a, b, x[i+10], 15, -1051523);
    b = md5_ii(b, c, d, a, x[i+ 1], 21, -2054922799);
    a = md5_ii(a, b, c, d, x[i+ 8], 6 ,  1873313359);
    d = md5_ii(d, a, b, c, x[i+15], 10, -30611744);
    c = md5_ii(c, d, a, b, x[i+ 6], 15, -1560198380);
    b = md5_ii(b, c, d, a, x[i+13], 21,  1309151649);
    a = md5_ii(a, b, c, d, x[i+ 4], 6 , -145523070);
    d = md5_ii(d, a, b, c, x[i+11], 10, -1120210379);
    c = md5_ii(c, d, a, b, x[i+ 2], 15,  718787259);
    b = md5_ii(b, c, d, a, x[i+ 9], 21, -343485551);

    a = safe_add(a, olda);
    b = safe_add(b, oldb);
    c = safe_add(c, oldc);
    d = safe_add(d, oldd);
  }
  return Array(a, b, c, d);
}

/*
 * These functions implement the four basic operations the algorithm uses.
 */
function md5_cmn(q, a, b, x, s, t)
{
  return safe_add(bit_rol(safe_add(safe_add(a, q), safe_add(x, t)), s),b);
}
function md5_ff(a, b, c, d, x, s, t)
{
  return md5_cmn((b & c) | ((~b) & d), a, b, x, s, t);
}
function md5_gg(a, b, c, d, x, s, t)
{
  return md5_cmn((b & d) | (c & (~d)), a, b, x, s, t);
}
function md5_hh(a, b, c, d, x, s, t)
{
  return md5_cmn(b ^ c ^ d, a, b, x, s, t);
}
function md5_ii(a, b, c, d, x, s, t)
{
  return md5_cmn(c ^ (b | (~d)), a, b, x, s, t);
}

/*
 * Add integers, wrapping at 2^32. This uses 16-bit operations internally
 * to work around bugs in some JS interpreters.
 */
function safe_add(x, y)
{
  var lsw = (x & 0xFFFF) + (y & 0xFFFF);
  var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
  return (msw << 16) | (lsw & 0xFFFF);
}

/*
 * Bitwise rotate a 32-bit number to the left.
 */
function bit_rol(num, cnt)
{
  return (num << cnt) | (num >>> (32 - cnt));
}

</script>

<script>
var begin = new Date();
var rand = String(Math.random());
for (var i = 0; i < 1000000; i++) {    
    hex_md5(rand);
}
var end = new Date();
document.write(end.getTime() - begin.getTime());
</script>

结果是 6216 左右，单位是毫秒，这里跑了 100 万次，那么就是说每次才 6.216 个微秒。

接下来是 SHA1

<script>
/*
 * A JavaScript implementation of the Secure Hash Algorithm, SHA-1, as defined
 * in FIPS 180-1
 * Version 2.2 Copyright Paul Johnston 2000 - 2009.
 * Other contributors: Greg Holt, Andrew Kepert, Ydnar, Lostinet
 * Distributed under the BSD License
 * See http://pajhome.org.uk/crypt/md5 for details.
 */

/*
 * Configurable variables. You may need to tweak these to be compatible with
 * the server-side, but the defaults work in most cases.
 */
var hexcase = 0;  /* hex output format. 0 - lowercase; 1 - uppercase        */
var b64pad  = ""; /* base-64 pad character. "=" for strict RFC compliance   */

/*
 * These are the functions you'll usually want to call
 * They take string arguments and return either hex or base-64 encoded strings
 */
function hex_sha1(s)    { return rstr2hex(rstr_sha1(str2rstr_utf8(s))); }
function b64_sha1(s)    { return rstr2b64(rstr_sha1(str2rstr_utf8(s))); }
function any_sha1(s, e) { return rstr2any(rstr_sha1(str2rstr_utf8(s)), e); }
function hex_hmac_sha1(k, d)
  { return rstr2hex(rstr_hmac_sha1(str2rstr_utf8(k), str2rstr_utf8(d))); }
function b64_hmac_sha1(k, d)
  { return rstr2b64(rstr_hmac_sha1(str2rstr_utf8(k), str2rstr_utf8(d))); }
function any_hmac_sha1(k, d, e)
  { return rstr2any(rstr_hmac_sha1(str2rstr_utf8(k), str2rstr_utf8(d)), e); }

/*
 * Perform a simple self-test to see if the VM is working
 */
function sha1_vm_test()
{
  return hex_sha1("abc").toLowerCase() == "a9993e364706816aba3e25717850c26c9cd0d89d";
}

/*
 * Calculate the SHA1 of a raw string
 */
function rstr_sha1(s)
{
  return binb2rstr(binb_sha1(rstr2binb(s), s.length * 8));
}

/*
 * Calculate the HMAC-SHA1 of a key and some data (raw strings)
 */
function rstr_hmac_sha1(key, data)
{
  var bkey = rstr2binb(key);
  if(bkey.length > 16) bkey = binb_sha1(bkey, key.length * 8);

  var ipad = Array(16), opad = Array(16);
  for(var i = 0; i < 16; i++)
  {
    ipad[i] = bkey[i] ^ 0x36363636;
    opad[i] = bkey[i] ^ 0x5C5C5C5C;
  }

  var hash = binb_sha1(ipad.concat(rstr2binb(data)), 512 + data.length * 8);
  return binb2rstr(binb_sha1(opad.concat(hash), 512 + 160));
}

/*
 * Convert a raw string to a hex string
 */
function rstr2hex(input)
{
  try { hexcase } catch(e) { hexcase=0; }
  var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
  var output = "";
  var x;
  for(var i = 0; i < input.length; i++)
  {
    x = input.charCodeAt(i);
    output += hex_tab.charAt((x >>> 4) & 0x0F)
           +  hex_tab.charAt( x        & 0x0F);
  }
  return output;
}

/*
 * Convert a raw string to a base-64 string
 */
function rstr2b64(input)
{
  try { b64pad } catch(e) { b64pad=''; }
  var tab = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
  var output = "";
  var len = input.length;
  for(var i = 0; i < len; i += 3)
  {
    var triplet = (input.charCodeAt(i) << 16)
                | (i + 1 < len ? input.charCodeAt(i+1) << 8 : 0)
                | (i + 2 < len ? input.charCodeAt(i+2)      : 0);
    for(var j = 0; j < 4; j++)
    {
      if(i * 8 + j * 6 > input.length * 8) output += b64pad;
      else output += tab.charAt((triplet >>> 6*(3-j)) & 0x3F);
    }
  }
  return output;
}

/*
 * Convert a raw string to an arbitrary string encoding
 */
function rstr2any(input, encoding)
{
  var divisor = encoding.length;
  var remainders = Array();
  var i, q, x, quotient;

  /* Convert to an array of 16-bit big-endian values, forming the dividend */
  var dividend = Array(Math.ceil(input.length / 2));
  for(i = 0; i < dividend.length; i++)
  {
    dividend[i] = (input.charCodeAt(i * 2) << 8) | input.charCodeAt(i * 2 + 1);
  }

  /*
   * Repeatedly perform a long division. The binary array forms the dividend,
   * the length of the encoding is the divisor. Once computed, the quotient
   * forms the dividend for the next step. We stop when the dividend is zero.
   * All remainders are stored for later use.
   */
  while(dividend.length > 0)
  {
    quotient = Array();
    x = 0;
    for(i = 0; i < dividend.length; i++)
    {
      x = (x << 16) + dividend[i];
      q = Math.floor(x / divisor);
      x -= q * divisor;
      if(quotient.length > 0 || q > 0)
        quotient[quotient.length] = q;
    }
    remainders[remainders.length] = x;
    dividend = quotient;
  }

  /* Convert the remainders to the output string */
  var output = "";
  for(i = remainders.length - 1; i >= 0; i--)
    output += encoding.charAt(remainders[i]);

  /* Append leading zero equivalents */
  var full_length = Math.ceil(input.length * 8 /
                                    (Math.log(encoding.length) / Math.log(2)))
  for(i = output.length; i < full_length; i++)
    output = encoding[0] + output;

  return output;
}

/*
 * Encode a string as utf-8.
 * For efficiency, this assumes the input is valid utf-16.
 */
function str2rstr_utf8(input)
{
  var output = "";
  var i = -1;
  var x, y;

  while(++i < input.length)
  {
    /* Decode utf-16 surrogate pairs */
    x = input.charCodeAt(i);
    y = i + 1 < input.length ? input.charCodeAt(i + 1) : 0;
    if(0xD800 <= x && x <= 0xDBFF && 0xDC00 <= y && y <= 0xDFFF)
    {
      x = 0x10000 + ((x & 0x03FF) << 10) + (y & 0x03FF);
      i++;
    }

    /* Encode output as utf-8 */
    if(x <= 0x7F)
      output += String.fromCharCode(x);
    else if(x <= 0x7FF)
      output += String.fromCharCode(0xC0 | ((x >>> 6 ) & 0x1F),
                                    0x80 | ( x         & 0x3F));
    else if(x <= 0xFFFF)
      output += String.fromCharCode(0xE0 | ((x >>> 12) & 0x0F),
                                    0x80 | ((x >>> 6 ) & 0x3F),
                                    0x80 | ( x         & 0x3F));
    else if(x <= 0x1FFFFF)
      output += String.fromCharCode(0xF0 | ((x >>> 18) & 0x07),
                                    0x80 | ((x >>> 12) & 0x3F),
                                    0x80 | ((x >>> 6 ) & 0x3F),
                                    0x80 | ( x         & 0x3F));
  }
  return output;
}

/*
 * Encode a string as utf-16
 */
function str2rstr_utf16le(input)
{
  var output = "";
  for(var i = 0; i < input.length; i++)
    output += String.fromCharCode( input.charCodeAt(i)        & 0xFF,
                                  (input.charCodeAt(i) >>> 8) & 0xFF);
  return output;
}

function str2rstr_utf16be(input)
{
  var output = "";
  for(var i = 0; i < input.length; i++)
    output += String.fromCharCode((input.charCodeAt(i) >>> 8) & 0xFF,
                                   input.charCodeAt(i)        & 0xFF);
  return output;
}

/*
 * Convert a raw string to an array of big-endian words
 * Characters >255 have their high-byte silently ignored.
 */
function rstr2binb(input)
{
  var output = Array(input.length >> 2);
  for(var i = 0; i < output.length; i++)
    output[i] = 0;
  for(var i = 0; i < input.length * 8; i += 8)
    output[i>>5] |= (input.charCodeAt(i / 8) & 0xFF) << (24 - i % 32);
  return output;
}

/*
 * Convert an array of big-endian words to a string
 */
function binb2rstr(input)
{
  var output = "";
  for(var i = 0; i < input.length * 32; i += 8)
    output += String.fromCharCode((input[i>>5] >>> (24 - i % 32)) & 0xFF);
  return output;
}

/*
 * Calculate the SHA-1 of an array of big-endian words, and a bit length
 */
function binb_sha1(x, len)
{
  /* append padding */
  x[len >> 5] |= 0x80 << (24 - len % 32);
  x[((len + 64 >> 9) << 4) + 15] = len;

  var w = Array(80);
  var a =  1732584193;
  var b = -271733879;
  var c = -1732584194;
  var d =  271733878;
  var e = -1009589776;

  for(var i = 0; i < x.length; i += 16)
  {
    var olda = a;
    var oldb = b;
    var oldc = c;
    var oldd = d;
    var olde = e;

    for(var j = 0; j < 80; j++)
    {
      if(j < 16) w[j] = x[i + j];
      else w[j] = bit_rol(w[j-3] ^ w[j-8] ^ w[j-14] ^ w[j-16], 1);
      var t = safe_add(safe_add(bit_rol(a, 5), sha1_ft(j, b, c, d)),
                       safe_add(safe_add(e, w[j]), sha1_kt(j)));
      e = d;
      d = c;
      c = bit_rol(b, 30);
      b = a;
      a = t;
    }

    a = safe_add(a, olda);
    b = safe_add(b, oldb);
    c = safe_add(c, oldc);
    d = safe_add(d, oldd);
    e = safe_add(e, olde);
  }
  return Array(a, b, c, d, e);

}

/*
 * Perform the appropriate triplet combination function for the current
 * iteration
 */
function sha1_ft(t, b, c, d)
{
  if(t < 20) return (b & c) | ((~b) & d);
  if(t < 40) return b ^ c ^ d;
  if(t < 60) return (b & c) | (b & d) | (c & d);
  return b ^ c ^ d;
}

/*
 * Determine the appropriate additive constant for the current iteration
 */
function sha1_kt(t)
{
  return (t < 20) ?  1518500249 : (t < 40) ?  1859775393 :
         (t < 60) ? -1894007588 : -899497514;
}

/*
 * Add integers, wrapping at 2^32. This uses 16-bit operations internally
 * to work around bugs in some JS interpreters.
 */
function safe_add(x, y)
{
  var lsw = (x & 0xFFFF) + (y & 0xFFFF);
  var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
  return (msw << 16) | (lsw & 0xFFFF);
}

/*
 * Bitwise rotate a 32-bit number to the left.
 */
function bit_rol(num, cnt)
{
  return (num << cnt) | (num >>> (32 - cnt));
}

</script>

<script>
var begin = new Date();
var rand = String(Math.random());
for (var i = 0; i < 1000000; i++) {    
    hex_sha1(rand);
}
var end = new Date();
document.write(end.getTime() - begin.getTime());
</script>

结果是 8184，比 MD5 慢一点点，每个是 8.184 个微秒

附上我的机器配置：

OS 名称 Microsoft Windows 7 专业版版本 6.1.7601 Service Pack 1 内部版本 7601 系统类型 X86-based PC 处理器 Intel(R) Core(TM) i5-3470 CPU @ 3.20GHz，3201 Mhz，4 个内核，4 个逻辑处理器总的物理内存 3.34 GB

来自系统信息工具

浏览器是 chrome 26.0.1410.43 m，对应的 Javascript 引擎是 V8 3.16.14.9

-———————————————————————————–

2013-04-03 15:24:57 update IE 9 下的时间分别是 MD5 15658 ，SHA1 26091

MySQL 大量 insert 操作的效率优化

Tue, 15 Jan 2013 13:27:52 +0800

最近在重写 szucal 的爬虫，之前的爬虫是用 MFC 写的，虽然速度不错，但是写起来很麻烦，不便于交给他人维护，这次看中 PHP 的函数封装得好，很多东西直接拿来就可以用，于是就选了 PHP 来写，初步写完之后，尝试着跑了一下，发现效率惨不忍睹，把 PHP 脚本的时间 set_time_limit(10) 跑了一下得到下面的结果

mysql> show table status\G
*************************** 1. row ***************************
           Name: course
         Engine: InnoDB
        Version: 10
     Row_format: Compact
           Rows: 3
 Avg_row_length: 5461
    Data_length: 16384
Max_data_length: 0
   Index_length: 0
      Data_free: 27262976
 Auto_increment: 4
    Create_time: 2013-01-14 22:33:03
    Update_time: NULL
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 2. row ***************************
           Name: course_time_location
         Engine: InnoDB
        Version: 10
     Row_format: Compact
           Rows: 6
 Avg_row_length: 2730
    Data_length: 16384
Max_data_length: 0
   Index_length: 0
      Data_free: 27262976
 Auto_increment: 7
    Create_time: 2013-01-14 22:33:03
    Update_time: NULL
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 3. row ***************************
           Name: log
         Engine: InnoDB
        Version: 10
     Row_format: Compact
           Rows: 8
 Avg_row_length: 2048
    Data_length: 16384
Max_data_length: 0
   Index_length: 0
      Data_free: 27262976
 Auto_increment: 9
    Create_time: 2013-01-14 22:33:03
    Update_time: NULL
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 4. row ***************************
           Name: stu
         Engine: InnoDB
        Version: 10
     Row_format: Compact
           Rows: 85
 Avg_row_length: 192
    Data_length: 16384
Max_data_length: 0
   Index_length: 0
      Data_free: 27262976
 Auto_increment: 86
    Create_time: 2013-01-14 22:33:03
    Update_time: NULL
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 5. row ***************************
           Name: stu_course
         Engine: InnoDB
        Version: 10
     Row_format: Compact
           Rows: 86
 Avg_row_length: 190
    Data_length: 16384
Max_data_length: 0
   Index_length: 0
      Data_free: 27262976
 Auto_increment: 87
    Create_time: 2013-01-14 22:33:03
    Update_time: NULL
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
5 rows in set (0.00 sec)

mysql>

可以看到 10 秒钟下来，才处理了 3 页课程名单表，插入了 80 多个学生数据，以及 80 条选课关系，这么估算下来，深大一个学期大约有 4000 门课程，一门课程 3 秒的话，就是 3 个多小时，这个效率肯定是无法接受的，因为我原来的 MFC 爬虫爬完全部数据也才只需要 5 到 10 分钟。

出现了问题，于是就开始想是网络拉取数据那里慢了，还是数据库写入数据那里慢了，简单实验了一下，把封装的数据库类的写入函数注释掉，关掉了写入数据的部分，再跑了一下，发现下载全部数据并解析好只需要 8 分多钟，那么明显就是在 insert 数据的时候效率低下了。

搜了一下，看到这里，http://fred.oracle1.com/weblog/2010/09/08/mysql%E6%80%A7%E8%83%BD%E4%BC%98%E5%8C%9617-insert%E6%93%8D%E4%BD%9C%E7%9A%84%E4%BC%98%E5%8C%96/

执行 INSERT 操作的时候，可以考虑使用以下的方式优化 SQL 的执行效率：

如果你同时从同一客户插入很多行，使用多个值表的 INSERT 语句。这比使用分开 INSERT 语句快。 Insert into test values(1,2),(1,3),(1,4) … 如果你从不同客户插入很多行，能通过使用 INSERT DELAYED 语句得到更高的速度。 Delayed的含义是让 INSERT 语句马上执行，其实数据都被放在内存的队列中，并没有真正写入磁盘；这比每条语句分别插入要快的多； LOW_PRIORITY 刚好相反，在所有其他用户对表的读写完后才进行插入；将索引文件和数据文件分在不同的磁盘上存放；如果进行批量插入，可以增加 bulk_insert_buffer_size 变量值的方法来提高速度，但是，这只能对 MyISAM 表使用；当从一个文本文件装载一个表时，使用 LOAD DATA INFILE。这通常比使用很多 INSERT 语句快 20 倍；根据应用情况使用 REPLACE 语句代替 INSERT ；根据应用情况使用 IGNORE 关键字忽略重复记录。

有提到在一行当中并着写入多个 values 的，这个其实我之前的 MFC 爬虫就是这样的，因为 MFC 连接 MySQL 不方便，所以当时我的做法就是根据 MySQL 的导入导出文件的格式，在爬取数据的时候，自己生成一份格式相仿的导入文件，等到爬虫跑完了，再把那份文件导入到数据库中去，但是在这次的 PHP 中，如果要这么做，其实是不方便的，再看到后面有说使用 delayed 的，于是试了一下，查到这里，http://www.uml.org.cn/sjjm/201108293.asp

一、DELAYED 的使用

使用延迟插入操作DELAYED调节符应用于INSERT和REPLACE语句。当DELAYED插入操作到达的时候，服务器把数据行放入一个队列中，并立即给客户端返回一个状态信息，这样客户端就可以在数据表被真正地插入记录之前继续进行操作了。如果读取者从该数据表中读取数据，队列中的数据就会被保持着，直到没有读取者为止。

接着服务器开始插入延迟数据行（delayed-row）队列中的数据行。在插入操作的同时，服务器还要检查是否有新的读取请求到达和等待。如果有，延迟数据行队列就被挂起，允许读取者继续操作。当没有读取者的时候，服务器再次开始插入延迟的数据行。这个过程一直进行，直到队列空了为止。

几点要注意事项：

INSERT DELAYED应该仅用于指定值清单的INSERT语句。服务器忽略用于INSERT DELAYED…SELECT语句的DELAYED。服务器忽略用于INSERT DELAYED…ON DUPLICATE UPDATE语句的DELAYED。

因为在行被插入前，语句立刻返回，所以您不能使用LAST_INSERT_ID()来获取AUTO_INCREMENT值。AUTO_INCREMENT值可能由语句生成。

对于SELECT语句，DELAYED行不可见，直到这些行确实被插入了为止。

DELAYED在从属复制服务器中被忽略了，因为DELAYED不会在从属服务器中产生与主服务器不一样的数据。注意，目前在队列中的各行只保存在存储器中，直到它们被插入到表中为止。这意味着，如果您强行中止了mysqld(例如，使用kill -9)或者如果mysqld意外停止，则所有没有被写入磁盘的行都会丢失。

另外由于 delayed 用法只能在 MyISAM 中支持，所以先把数据引擎从 InnoDB 换成 MyISAM，换过来之后，先跑一个 10 秒的测试

mysql> show table status\G
*************************** 1. row ***************************
           Name: course
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 104
 Avg_row_length: 148
    Data_length: 15404
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 105
    Create_time: 2013-01-15 11:53:59
    Update_time: 2013-01-15 11:54:53
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 2. row ***************************
           Name: course_time_location
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 155
 Avg_row_length: 43
    Data_length: 6756
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 156
    Create_time: 2013-01-15 11:53:59
    Update_time: 2013-01-15 11:54:53
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 3. row ***************************
           Name: log
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 114
 Avg_row_length: 137
    Data_length: 15680
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 115
    Create_time: 2013-01-15 11:53:59
    Update_time: 2013-01-15 11:54:53
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 4. row ***************************
           Name: stu
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 1901
 Avg_row_length: 51
    Data_length: 97468
Max_data_length: 281474976710655
   Index_length: 21504
      Data_free: 0
 Auto_increment: 1902
    Create_time: 2013-01-15 11:53:59
    Update_time: 2013-01-15 11:54:53
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 5. row ***************************
           Name: stu_course
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 5499
 Avg_row_length: 31
    Data_length: 170520
Max_data_length: 281474976710655
   Index_length: 57344
      Data_free: 0
 Auto_increment: 5500
    Create_time: 2013-01-15 11:53:59
    Update_time: 2013-01-15 11:54:53
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
5 rows in set (0.00 sec)

mysql>

惊讶的看到，只是简单的换了一个引擎，没有改动代码，就可以得到如此之高的效率提升，10 秒钟处理的课程量达到了 104 门，写入了 1901 个学生的信息和 5499 条选课关系，这么算的话，4000 门课程只需要 400 秒左右，下面试一下使用 delayed，注意到代码中有一个地方是写入学生信息数据的，在写入一个学生之前，要先 select 一下，但是使用了 delayed 之后，就会导致 select 的结果不准确，于是需要使用 ignore，看这里，http://www.uml.org.cn/sjjm/201108293.asp

二、IGNORE的使用

IGNORE是MySQL相对于标准SQL的扩展。如果在新表中有重复关键字，或者当STRICT模式启动后出现警告，则使用IGNORE控制ALTER TABLE的运行。

如果没有指定IGNORE，当重复关键字错误发生时，复制操作被放弃，返回前一步骤。

如果指定了IGNORE，则对于有重复关键字的行，只使用第一行，其它有冲突的行被删除。并且，对错误值进行修正，使之尽量接近正确值。insert ignore into tb(…) value(…)这样不用校验是否存在了，有则忽略，无则添加。

原来的代码是这样的

// 写入学生表之前先检查是否存在			
$query = "select * from $t_stu where stu_id = ?";
$dbr = $this->db->query($query, $stu_id);
if (count($dbr) == 0) {
	// 不存在该学生的信息
	$query = "insert delayed into $t_stu (stu_id, stu_name, sex, class) values (?, ?, ?, ?)";
	$this->db->query($query, array($stu_id, $stu_name, $sex, $class));
}

修改之后代码变成这样

// 写入学生表	
$query = "insert delayed ignore into $t_stu (stu_id, stu_name, sex, class) values (?, ?, ?, ?)";
$this->db->query($query, array($stu_id, $stu_name, $sex, $class));

跑一个 10 秒测试的结果如下

mysql> show table status\G
*************************** 1. row ***************************
           Name: course
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 171
 Avg_row_length: 150
    Data_length: 25812
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 172
    Create_time: 2013-01-15 12:46:53
    Update_time: 2013-01-15 12:47:11
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 2. row ***************************
           Name: course_time_location
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 224
 Avg_row_length: 42
    Data_length: 9456
Max_data_length: 281474976710655
   Index_length: 5120
      Data_free: 0
 Auto_increment: 225
    Create_time: 2013-01-15 12:46:53
    Update_time: 2013-01-15 12:47:11
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 3. row ***************************
           Name: log
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 181
 Avg_row_length: 139
    Data_length: 25292
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 182
    Create_time: 2013-01-15 12:46:53
    Update_time: 2013-01-15 12:47:01
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 4. row ***************************
           Name: stu
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 9259
 Avg_row_length: 50
    Data_length: 465700
Max_data_length: 281474976710655
   Index_length: 97280
      Data_free: 0
 Auto_increment: 9260
    Create_time: 2013-01-15 12:46:53
    Update_time: 2013-01-15 12:47:11
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 5. row ***************************
           Name: stu_course
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 9259
 Avg_row_length: 31
    Data_length: 287164
Max_data_length: 281474976710655
   Index_length: 97280
      Data_free: 0
 Auto_increment: 9260
    Create_time: 2013-01-15 12:46:53
    Update_time: 2013-01-15 12:47:11
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
5 rows in set (0.00 sec)

mysql>

可以看到速度依然能够有所提升，10 秒钟写入了 170 门课和 9200 多个学生信息以及 9200 多条选课记录，不过这里可以注意到学生信息的条数应该是出了问题的，核查数据也确实可以发现学生信息发生了重复，那么试试对 stu_id 建一个索引

ALTER TABLE  `stu` ADD UNIQUE (`stu_id`)

再跑一个测试

mysql> show table status\G
*************************** 1. row ***************************
           Name: course
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 160
 Avg_row_length: 148
    Data_length: 23752
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 161
    Create_time: 2013-01-15 13:22:06
    Update_time: 2013-01-15 13:22:59
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 2. row ***************************
           Name: course_time_location
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 213
 Avg_row_length: 42
    Data_length: 9060
Max_data_length: 281474976710655
   Index_length: 5120
      Data_free: 0
 Auto_increment: 214
    Create_time: 2013-01-15 13:22:06
    Update_time: 2013-01-15 13:22:59
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 3. row ***************************
           Name: log
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 170
 Avg_row_length: 139
    Data_length: 23684
Max_data_length: 281474976710655
   Index_length: 4096
      Data_free: 0
 Auto_increment: 171
    Create_time: 2013-01-15 13:22:06
    Update_time: 2013-01-15 13:22:59
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 4. row ***************************
           Name: stu
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 2620
 Avg_row_length: 50
    Data_length: 132944
Max_data_length: 281474976710655
   Index_length: 82944
      Data_free: 0
 Auto_increment: 2621
    Create_time: 2013-01-15 13:22:14
    Update_time: 2013-01-15 13:22:59
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
*************************** 5. row ***************************
           Name: stu_course
         Engine: MyISAM
        Version: 10
     Row_format: Dynamic
           Rows: 8740
 Avg_row_length: 31
    Data_length: 271792
Max_data_length: 281474976710655
   Index_length: 92160
      Data_free: 0
 Auto_increment: 8741
    Create_time: 2013-01-15 13:22:06
    Update_time: 2013-01-15 13:22:59
     Check_time: NULL
      Collation: utf8_general_ci
       Checksum: NULL
 Create_options:
        Comment:
5 rows in set (0.00 sec)

mysql>

效率稍有下降，160 多门课程名单，2600 多个学生信息以及 8700 多条选课关系，不过这样起码保证了学生信息的唯一性。

最后附上一些官方文档，INSERT语句的速度，http://dev.mysql.com/doc/refman/5.1/zh/optimization.html#insert-speed，INSERT Syntax，http://dev.mysql.com/doc/refman/5.5/en/insert.html，INSERT DELAYED Syntax，http://dev.mysql.com/doc/refman/5.1/en/insert-delayed.html，另外，还有一个据说效率更高的 load data infile 用法，但是这个是适用于从文件中读入数据的，LOAD DATA INFILE语法，http://dev.mysql.com/doc/refman/5.1/zh/sql-syntax.html#load-data